55:, which involves creating an actual text in a human language (English, French, etc.) from a syntactic representation. There are a number of software packages available for realization, most of which have been developed by academic research groups in NLG. The remainder of this article concerns realization of this kind.
301:
A number of realisers have been developed over the past 20 years. These systems differ in terms of complexity and sophistication of their processing, robustness in dealing with unusual cases, and whether they are accessed programmatically via an API or whether they take a textual representation of a
235:
In this example, the computer program has specified the linguistic constituents of the sentence (verb, subject), and also linguistic features (plural subject, negated), and from this information the realiser has constructed the actual sentence.
250:: Using grammatical knowledge to choose inflections, add function words and also to decide the order of components. For example, in English the subject usually precedes the verb, and the negated form of
317:: a document realizing engine with an api which intended to be simple to learn and use, focused on limiting scope to only finding the surface area of a document.
325:: this is the oldest realiser, which has been under development under different guises since the 1980s. It comes with grammars for ten different languages.
341:: an open-source realiser which has a number of nice features, such as the ability to use statistical language models to make realisation decisions.
391:
396:
305:
There are also major differences in pragmatic factors such as documentation, support, licensing terms, speed and memory usage, etc.
64:
52:
376:
25:
293:
The above examples are very basic, most realisers are capable of considerably more complex processing.
358:
A Gatt and E Reiter (2009). SimpleNLG: A realisation engine for practical applications.
333:: a realiser which was widely used in the 1990s, and is still used in some projects today
308:
It is not possible to describe all realisers here, but a few of the emerging areas are:
385:
41:
283:
29:
17:
362:
28:
is derived from its underlying representation; that is, the way in which some
45:
44:. The different sounds that can realize a particular phoneme are called its
315:
378:- ACL NLG Portal (contains links to the above and many other realisers)
33:
32:
object of linguistic analysis comes to be produced in actual language.
72:
339:
331:
323:
264:: Computing inflected forms, for example the plural form of
244:Realisation involves three kinds of processing:
290:because it is the first word of the sentence.
286:, and formatting. For example, capitalising
8:
351:
24:is the process by which some kind of
7:
302:syntactic structure as their input.
14:
51:Realization is also a subtask of
1:
392:Natural language processing
63:For example, the following
53:natural language generation
413:
397:Computational linguistics
262:Morphological realisation
280:Orthographic realisation
80:
282:: Dealing with casing,
76:The women do not smoke.
74:to print out the text
26:surface representation
360:Proceedings of ENLG09
248:Syntactic realisation
36:are often said to be
161:"smoke"
110:"woman"
404:
364:
356:
231:
228:
225:
222:
219:
216:
213:
210:
207:
204:
201:
198:
195:
192:
189:
186:
183:
180:
177:
174:
171:
168:
165:
162:
159:
156:
153:
150:
147:
144:
141:
138:
135:
132:
129:
126:
123:
120:
117:
114:
111:
108:
105:
102:
99:
98:createNounPhrase
96:
93:
90:
87:
84:
67:code causes the
412:
411:
407:
406:
405:
403:
402:
401:
382:
381:
373:
368:
367:
357:
353:
348:
299:
242:
233:
232:
229:
226:
223:
221:realiseSentence
220:
217:
214:
211:
208:
205:
202:
199:
196:
193:
190:
187:
184:
181:
178:
175:
172:
169:
166:
163:
160:
157:
154:
151:
148:
145:
142:
139:
136:
133:
130:
127:
124:
121:
118:
115:
112:
109:
106:
104:"the"
103:
100:
97:
94:
91:
88:
85:
82:
61:
12:
11:
5:
410:
408:
400:
399:
394:
384:
383:
380:
379:
372:
371:External links
369:
366:
365:
350:
349:
347:
344:
343:
342:
334:
326:
318:
298:
295:
241:
238:
81:
60:
57:
13:
10:
9:
6:
4:
3:
2:
409:
398:
395:
393:
390:
389:
387:
377:
375:
374:
370:
363:
361:
355:
352:
345:
340:
338:
335:
332:
330:
327:
324:
322:
319:
316:
314:
311:
310:
309:
306:
303:
296:
294:
291:
289:
285:
281:
277:
275:
271:
267:
263:
259:
257:
253:
249:
245:
239:
237:
79:
77:
73:
70:
66:
58:
56:
54:
49:
47:
43:
42:speech sounds
39:
35:
31:
27:
23:
19:
359:
354:
336:
328:
320:
312:
307:
304:
300:
292:
287:
279:
278:
273:
269:
265:
261:
260:
256:do not smoke
255:
251:
247:
246:
243:
234:
149:createClause
83:NPPhraseSpec
75:
68:
62:
50:
37:
21:
15:
284:punctuation
134:SPhraseSpec
22:realization
18:linguistics
386:Categories
346:References
240:Processing
173:setFeature
143:nlgFactory
92:nlgFactory
46:allophones
329:FUF/SURGE
313:Simplenlg
122:setPlural
69:simplenlg
227:sentence
215:realiser
167:sentence
137:sentence
38:realized
34:Phonemes
30:abstract
337:OpenCCG
297:Systems
209:println
185:NEGATED
179:Feature
155:subject
116:subject
86:subject
71:system
59:Example
274:womans
197:System
272:(not
270:women
266:woman
252:smoke
321:KPML
191:true
128:true
65:Java
288:The
276:).
268:is
254:is
230:));
203:out
40:by
16:In
388::
258:.
194:);
164:);
131:);
113:);
78::
48:.
20:,
224:(
218:.
212:(
206:.
200:.
188:,
182:.
176:(
170:.
158:,
152:(
146:.
140:=
125:(
119:.
107:,
101:(
95:.
89:=
Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.